lokalise-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions and code snippets that use execSync to run shell commands. Specifically, it demonstrates using curl to download translation bundles and unzip to extract them into the project directory. It also includes a Vite plugin example that executes npm run i18n:pull during the build process.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of translation assets from Lokalise's infrastructure. It retrieves authenticated S3 bundle URLs via the Lokalise API and downloads them using curl or axios for integration into the application.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external translation data, which establishes a surface for indirect prompt injection. 1. Ingestion points: Translation files (JSON, XLIFF, PO) fetched from the Lokalise API as shown in SKILL.md and references/implementation-guide.md. 2. Boundary markers: None present; the examples do not include delimiters or warnings to ignore instructions embedded within translation strings. 3. Capability inventory: The skill uses execSync for subprocess execution, fs.writeFileSync and AdmZip for file system writes, and axios/curl for network requests. 4. Sanitization: No sanitization or validation of the translation content is performed before writing files or generating TypeScript types.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:46 AM
Security Audit — agent-trust-hub — lokalise-core-workflow-b